R Notebook

data <- read.csv('~/gr5243/philosophy_data.csv')

unique(data$author)

 [1] "Plato"           "Aristotle"       "Locke"           "Hume"            "Berkeley"        "Spinoza"         "Leibniz"         "Descartes"      
 [9] "Malebranche"     "Russell"         "Moore"           "Wittgenstein"    "Lewis"           "Quine"           "Popper"          "Kripke"         
[17] "Foucault"        "Derrida"         "Deleuze"         "Merleau-Ponty"   "Husserl"         "Heidegger"       "Kant"            "Fichte"         
[25] "Hegel"           "Marx"            "Lenin"           "Smith"           "Ricardo"         "Keynes"          "Epictetus"       "Marcus Aurelius"
[33] "Nietzsche"       "Wollstonecraft"  "Beauvoir"        "Davis"          

unique(data$original_publication_date)

 [1] -350 -320 1689 1739 1779 1713 1710 1677 1637 1641 1674 1921 1912 1910 1953 1985 1950 1959 1972 1975 1963 1961 1966 1967 1968 1945 1936 1907 1927
[30] 1788 1790 1781 1798 1817 1807 1820 1883 1848 1862 1776  125  170 1888 1886 1887 1792 1949 1981

library(tidytext)
data_words <- data %>%
  unnest_tokens(word, tokenized_txt)
data_count <- data_words %>%
  group_by(author, word) %>%
  count()
data(stop_words)
data_count_use <- data_count %>%
  anti_join(stop_words)

Joining, by = "word"

topwords <- data_count_use %>%
  group_by(author) %>%
  top_n(1, n)
ggplot(topwords, aes(x = reorder(word, n), y = n, fill = author)) +
  geom_col() +
  xlab(NULL) +
  coord_flip() +
  ggtitle("Top common word by each author") +
  xlab("Word") +
  ylab("Frequency")

library(dplyr)
library(ggplot2)
data_avg <- data %>%
  group_by(author) %>%
  summarize(avg_sentence_length = mean(sentence_length))
ggplot(data_avg, aes(x = avg_sentence_length, y = author)) +
  geom_bar(stat = "identity") +
  ggtitle("Average sentence length by author") +
  xlab("Average sentence length") +
  ylab("Author")

library(ggplot2)
data_avgschool <- data %>%
  group_by(school) %>%
  summarize(avg_sentence_length1 = mean(sentence_length))
ggplot(data_avgschool, aes(x = avg_sentence_length1, y = school)) +
  geom_bar(stat = "identity") +
  ggtitle("Average sentence length by school") +
  xlab("Average sentence length") +
  ylab("School")

descartes <- data %>% filter(author == "Descartes")
descartes_word <- descartes %>% unnest_tokens(word, tokenized_txt) %>% count(word, sort = TRUE)
descartes_word_use <- descartes_word %>%
  anti_join(stop_words)

Joining, by = "word"

descartes_top <- head(descartes_word_use, 20)
descartes_bot <- tail(descartes_word_use, 20)
ggplot(descartes_top, aes(x = reorder(word, n), y = n)) +
  geom_col() +
  xlab(NULL) +
  ggtitle("Top 20 words by Descartes") +
  xlab("Word") +
  ylab("Frequency")

wittgenstein <- data %>% filter(author == "Wittgenstein")
wittgenstein_word <- wittgenstein %>% unnest_tokens(word, tokenized_txt) %>% count(word, sort = TRUE)
wittgenstein_word_use <- wittgenstein_word %>%
anti_join(stop_words)

Joining, by = "word"

wittgenstein_top <- head(wittgenstein_word_use, 20)
wittgenstein_bot <- tail(wittgenstein_word_use, 20)
ggplot(wittgenstein_top, aes(x = reorder(word, n), y = n)) +
  geom_col() +
  xlab(NULL) +
  ggtitle("Top 20 words by Wittgenstein") +
  xlab("Word") +
  ylab("Frequency")

library(tidytext)
library(textdata)
get_sentiments("nrc")

d_nrc_positive <- get_sentiments("nrc") %>%
  filter(sentiment == "positive")

data_words %>%
  filter(author == "Descartes") %>%
  inner_join(d_nrc_positive) %>%
  count(word,sort = TRUE)

Joining, by = "word"

d_nrc_negative <- get_sentiments("nrc") %>%
  filter(sentiment == "negative")

data_words %>%
  filter(author == "Descartes") %>%
  inner_join(d_nrc_negative) %>%
  count(word,sort = TRUE)

Joining, by = "word"

w_nrc_positive <- get_sentiments("nrc") %>%
  filter(sentiment == "positive")

data_words %>%
  filter(author == "Wittgenstein") %>%
  inner_join(w_nrc_positive) %>%
  count(word,sort = TRUE)

Joining, by = "word"

w_nrc_negative <- get_sentiments("nrc") %>%
  filter(sentiment == "negative")

data_words %>%
  filter(author == "Wittgenstein") %>%
  inner_join(w_nrc_negative) %>%
  count(word,sort = TRUE)

Joining, by = "word"

library(sentimentr)
descartes_data <- data[data$author == "Descartes",]
descartes_data1 <- descartes_data$sentence_spacy
sentiment_scores <- sentiment(descartes_data1)

Warning: Each time `sentiment` is run it has to do sentence boundary disambiguation when a
raw `character` vector is passed to `text.var`. This may be costly of time and
memory.  It is highly recommended that the user first runs the raw `character`
vector through the `get_sentences` function.

head(sentiment_scores,20)

library(sentimentr)
wittgenstein_data <- data[data$author == "Wittgenstein",]
wittgenstein_data1 <- wittgenstein_data$sentence_spacy
sentiment_scores1 <- sentiment(wittgenstein_data1)

Warning: Each time `sentiment` is run it has to do sentence boundary disambiguation when a
raw `character` vector is passed to `text.var`. This may be costly of time and
memory.  It is highly recommended that the user first runs the raw `character`
vector through the `get_sentences` function.

head(sentiment_scores1,20)